Football Pass Prediction Using Player Locations
In many sports, predicting the passing behavior of players is desirable at it provides insights that can help to understand and improve player performance. In this paper, we describe a novel model for football pass prediction, developed to participate in the Prediction Challenge of the 5th Workshop on Machine Learning and Data Mining for Sports Analytics, collocated with ECML PAKDD 2018. The model called Football Pass Predictor (FPP) considers various aspects to generate predictions such as the distance between players, the proximity of players from the opposite team, and the direction of each pass. Experimental results shows that the model can achieve a prediction accuracy of 33.8%, and more than 50% if two guesses are allowed. This is considerably more than the random predictor, which obtains 8.3%.
KeywordsFootball Pass prediction Prediction challenge
This work is partially financed by the Youth 1000 talent funding of Philippe Fournier-Viger.
- 3.Plummer, B.T.: Analysis of attacking possessions leading to a goal attempt, and goal scoring patterns within men’s elite soccer. J. Sports Sci. Med. 1(1), 1–38 (2013)Google Scholar
- 4.Liu, T.: Systematische Spielbeobachtung im internationalen Leistungsfußball. Ph.D. dissertation. University of Bayreuth (2014)Google Scholar
- 5.Liu, T., Hohmann, A.: Apriori-based diagnostical analysis of passings in the football game. In: Proceedings of IEEE 2016 International Conference on Big Data Analysis, pp. 1–4. IEEE (2016)Google Scholar
- 6.Liu, T., Fournier-Viger, P., Hohmann, A.: Using diagnostic analysis to discover offensive patterns in a football game. In: Tavana, M., Patnaik, S. (eds.) Recent Developments in Data Science and Business Analytics. SPBE, pp. 381–386. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-72745-5_43CrossRefGoogle Scholar
- 7.Fournier-Viger, P., Nkambou, R., Tseng, S.M.: RuleGrowth: mining sequential rules common to several sequences by pattern-growth. In: Proceedings of 26th Symposium on Applied Computing, pp. 954–959. ACM Press (2011)Google Scholar
- 9.Fournier-Viger, P., Lin, J.C.-W., Kiran, R.U., Koh, Y.S., Thomas, R.: A survey of sequential pattern mining. Data Sci. Pattern Recogn. (DSPR) 1(1), 54–77 (2017)Google Scholar
- 10.Stöckl, M., Cruz, D., Duarte, R.: Modelling the tactical difficulty of passes in soccer. In: Chung, P., Soltoggio, A., Dawson, C.W., Meng, Q., Pain, M. (eds.) Proceedings of the 10th International Symposium on Computer Science in Sports (ISCSS). AISC, vol. 392, pp. 139–143. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-24560-7_17CrossRefGoogle Scholar
- 12.Gyarmati, L., Stanojevic, R.: QPass: a merit-based evaluation of soccer passes. Preprint on arXiv:1608.03532 (2016)
- 14.Cakmak, A., Uzun, A., Delibas, E.: Computational modeling of pass effectiveness in soccer. J. Adv. Complex Syst. (2018, in press)Google Scholar
- 15.Lida, R., Mase, K.: Ball passing course creating behavior in soccer game detection from player trajectory. IEICE Technical report, vol. 113, no. 432, pp. 171–176 (2014)Google Scholar
- 16.Dhar, J., Singh, A.: Game analysis and prediction of ball positions in a football match from video footages. In: Proceedings of International Conference on Recent Advances and Innovations in Engineering, pp. 1–6. IEEE (2014)Google Scholar